LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance

• URL: http://arxiv.org/abs/2605.22567v1
• Date: Thu, 21 May 2026 14:47:52 GMT
• Title: LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
• Abstract summary: Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models.<n>But its benefits have not fully translated to multilingual contexts.<n>We develop a novel framework that leverages language-conditioned hints to guide exploration in non-English reasoning tasks.
• Score: 77.58408743830314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off: prioritizing input-language consistency severely hampers reasoning quality, while prioritizing reasoning often leads to unintended language drift toward English. We address this challenge with LANG, a novel framework that leverages language-conditioned hints to guide exploration in non-English reasoning tasks. Our method incorporates two key mechanisms to prevent dependency on these hints: a progressive decay schedule that gradually withdraws scaffolding, and a language-adaptive switch that tailors learning horizons to specific language difficulties. Empirical results on challenging multilingual mathematical benchmarks reveal that LANG substantially enhances reasoning performance without compromising language consistency. Moreover, we show that our framework generalizes beyond mathematics, fostering more consistent language alignment across model layers

Related papers

• TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning [41.884158267107615]
  Large Language Models (LLMs) have demonstrated remarkable proficiency in English mathematical reasoning.<n>A significant performance disparity persists in multilingual contexts, largely attributed to deficiencies in language understanding.<n>We introduce Translation-Augmented Policy Optimization (TAPO), a novel reinforcement learning framework built upon GRPO.
  arXiv  Detail & Related papers  (2026-03-26T13:13:33Z)
• When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training [57.230355403478995]
  We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM.<n>We find that shared concept spaces emerge early and continue to refine, but that alignment with them is language-dependent.<n>In contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior.
  arXiv  Detail & Related papers  (2026-01-30T11:23:01Z)
• Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning [71.4175109189942]
  We present Pivot-Aligned Self-Feedback Multilingual Reasoning (PASMR)<n>This approach designates the model's primary language as the pivot language.<n>It establishes a cross-lingual self-feedback mechanism without relying on external correct answers or reward models.
  arXiv  Detail & Related papers  (2026-01-25T03:20:00Z)
• Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning [85.7304930030649]
  We propose M-Thinker, which is trained by a Language Consistency reward and a Cross-lingual Thinking Alignment reward.<n>M-Thinker achieves nearly 100% language consistency and superior performance on two multilingual benchmarks.
  arXiv  Detail & Related papers  (2025-10-08T17:55:02Z)
• SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models [39.13376984049828]
  We propose a training-free method that improves the performance on multilingual reasoning through a multi-step transformation.<n>The Structured-of-Thought (SoT) method converts language-specific semantic information into language-agnostic structured representations.<n> Experimental results demonstrate that SoT outperforms several strong baselines on multiple multilingual reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-03T01:02:14Z)
• Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? [59.970391602080205]
  Despite multilingual training, LRMs tend to default to reasoning in high-resource languages at test time.<n>Cultural reasoning degrades performance on reasoning tasks but benefits cultural tasks, while safety evaluations exhibit language-specific behavior.
  arXiv  Detail & Related papers  (2025-05-23T02:46:18Z)
• When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners [111.50503126693444]
  We show that language-specific ablation consistently boosts multilingual reasoning performance.<n>Compared to post-training, our training-free ablation achieves comparable or superior results with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-05-21T08:35:05Z)
• AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought [40.16140566668239]
  We introduce AdaMCOT, a framework that enhances multilingual factual reasoning.<n>AdaMCOT dynamically routing thought processes in intermediary "thinking languages" before generating target-language responses.<n>Our evaluation demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency.
  arXiv  Detail & Related papers  (2025-01-27T15:48:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.